22 citations · 76 across the 13 of their papers we have counts for
9 papers · 1 filter
How Transparent is DiffusionGemma?
Joshua Engels, Callum McDougall, Bilal Chughtai +11
LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, Diffus…
Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model
Jean Tarbouriech, Matteo Pirotta, Michal Valko +1
We study the sample complexity of learning an -optimal policy in the Stochastic Shortest Path (SSP) problem. We first derive sample complexity bounds when the learner has access…
Probabilistic Inference in Reinforcement Learning Done Right
Jean Tarbouriech, Tor Lattimore, Brendan O'Donoghue
A popular perspective in Reinforcement learning (RL) casts the problem as probabilistic inference on a graphical model of the Markov decision process (MDP). The core object of stud…
Adaptive Multi-Goal Exploration
Jean Tarbouriech, Omar Darwiche Domingues, Pierre Ménard +3
We introduce a generic strategy for provably efficient multi-goal exploration. It relies on AdaGoal, a novel goal selection scheme that leverages a measure of uncertainty in reachi…
Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching
Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier +2
Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning. A desirable and challenging unsupervised objective is to learn a set of div…
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
Jean Tarbouriech, Runlong Zhou, Simon S. Du +3
We study the problem of learning in the stochastic shortest path (SSP) setting, where an agent seeks to minimize the expected cost accumulated before reaching a goal state. We desi…
Improved Sample Complexity for Incremental Autonomous Exploration in MDPs
Jean Tarbouriech, Matteo Pirotta, Michal Valko +1
We investigate the exploration of an unknown environment when no reward function is provided. Building on the incremental exploration setting introduced by Lim and Auer [1], we def…
A Provably Efficient Sample Collection Strategy for Reinforcement Learning
Jean Tarbouriech, Matteo Pirotta, Michal Valko +1
One of the challenges in online reinforcement learning (RL) is that the agent needs to trade off the exploration of the environment and the exploitation of the samples to optimize…
Adversarial Attacks on Linear Contextual Bandits
Evrard Garcelon, Baptiste Roziere, Laurent Meunier +4
Contextual bandit algorithms are applied in a wide range of domains, from advertising to recommender systems, from clinical trials to education. In many of these domains, malicious…